# DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries

arXiv: https://arxiv.org/abs/2509.21825 · HTML: https://mlsanity.com/paper/2509.21825/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 20 of 20)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow](https://mlsanity.com/paper/2306.07209/) (2023)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models](https://mlsanity.com/paper/2410.07331/) (2024)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://mlsanity.com/paper/2505.14738/) (2025)
- [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025)
- [Benchmarking Data Science Agents](https://mlsanity.com/paper/2402.17168/) (2024)
- [ChatGPT as your Personal Data Scientist](https://mlsanity.com/paper/2305.13657/) (2023)
- [When Text Embedding Meets Large Language Model: A Comprehensive Survey](https://mlsanity.com/paper/2412.09165/) (2024)
- [DSCodeBench: A Realistic Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2505.15621/) (2025)

## Built on by (most cited first, 6 of 6)

- [Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis](https://mlsanity.com/paper/2604.24198/) (2026)
- [LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis](https://mlsanity.com/paper/2605.30434/) (2026)
- [LLMs can construct powerful representations and streamline sample-efficient supervised learning](https://mlsanity.com/paper/2603.11679/) (2026)
- [AIM: Agentic Idea Management for Automated Research](https://mlsanity.com/paper/2609.38445/) (2026)
- [An Auditable AI Agent Loop for Empirical Economics: A Case Study in Forecast Combination](https://mlsanity.com/paper/2603.17381/) (2026)
- [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring multiple sources and synthesizing open-ended insights. In this paper, we introduce DS-STAR, a specialized agent to bridge this gap. Unlike prior approaches, DS-STAR is designed to (1) seamlessly process and integrate data across diverse, heterogeneous formats, and (2) move beyond simple QA to generate comprehensive research reports for open-ended queries. Extensive evaluation shows that DS-STAR achieves state-of-the-art performance on four benchmarks: DABStep, DABStep-Research, KramaBench, and DA-Code. Most notably, it significantly outperforms existing baseline models especially in hard-level QA tasks requiring multi-file processing, and generates high-quality data science reports that are preferred over the best baseline model in over 88% of cases.